Classifying human leg motions with uniaxial piezoelectric gyroscopes
| Autor: | Kerem Altun, Billur Barshan, Orkun Tuncel |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2009 |
| Předmět: |
Least-squares method
gyroscope K-nearest neighbor Computer science Digital storage Gyroscopes 02 engineering and technology computer.software_genre lcsh:Chemical technology 01 natural sciences Biochemistry Least squares methods support vector machines Analytical Chemistry law.invention k-nearest neighbors algorithm Inertial sensor law 0202 electrical engineering electronic engineering information engineering Feature (machine learning) lcsh:TP1-1185 Instrumentation inertial sensors motion classification Bayesian decision making rule-based algorithm least-squares method k-nearest neighbor dynamic time warping artificial neural networks Artificial neural network Artificial neural networks Gyroscope Atomic and Molecular Physics and Optics Rule-based algorithm Bayesian decision makings Rule based algorithms 020201 artificial intelligence & image processing Data mining Inertial navigation systems Algorithms Neural networks Dynamic time warping Decision trees Decision tree Piezoelectricity Inertial sensors Article K-nearest neighbors Pattern recognition Electrical and Electronic Engineering Support vector machines business.industry 010401 analytical chemistry Motion classification 0104 chemical sciences Costs Support vector machine ComputingMethodologies_PATTERNRECOGNITION Artificial intelligence business computer Decision making |
| Zdroj: | Sensors Sensors, Vol 9, Iss 11, Pp 8508-8546 (2009) Sensors (Basel, Switzerland) Sensors; Volume 9; Issue 11; Pages: 8508-8546 |
| Popis: | This paper provides a comparative study on the different techniques of classifying human leg motions that are performed using two low-cost uniaxial piezoelectric gyroscopes worn on the leg. A number of feature sets, extracted from the raw inertial sensor data in different ways, are used in the classification process. The classification techniques implemented and compared in this study are: Bayesian decision making (BDM), a rule-based algorithm (RBA) or decision tree, least-squares method (LSM), k-nearest neighbor algorithm (k-NN), dynamic time warping (DTW), support vector machines (SVM), and artificial neural networks (ANN). A performance comparison of these classification techniques is provided in terms of their correct differentiation rates, confusion matrices, computational cost, and training and storage requirements. Three different cross-validation techniques are employed to validate the classifiers. The results indicate that BDM, in general, results in the highest correct classification rate with relatively small computational cost. © 2009 by the authors. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|